© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41317
    Prev
    Next
    INDEX
    Explanations

    between numbers and intervals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DET
    -0.07
    oslav
    -0.07
    orer
    -0.07
    æѤçĶŁ
    -0.07
    åħ¨æł¡å¸ĪçĶŁ
    -0.07
     Buc
    -0.06
    гови
    -0.06
    è£Ļ
    -0.06
    stdin
    -0.06
    é³Į
    -0.06
    POSITIVE LOGITS
     ìĤ¬ìĿ´ìĹIJ
    0.07
    Iteration
    0.07
    udas
    0.07
    æķ°æį®çº¿
    0.07
    ä¹ĭéĹ´æľī
    0.07
    ấp
    0.07
    Bindable
    0.07
    éĸĵãģ¯
    0.07
    ä¹ĭéĹ´çļĦæĦŁæĥħ
    0.07
     междÑĥ
    0.07
    Activations Density 0.007%

    No Known Activations